Arxiv:1910.09700 4-bit 4bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Instruct Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/zhoukz/qwen2-7b-instruct-4bit
Qwen2 7B Instruct 4bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen2 7B Instruct 4bit Parameters and Internals
| LLM Name | Qwen2 7B Instruct 4bit |
| Repository 🤗 | https://huggingface.co/zhoukz/qwen2-7b-instruct-4bit |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 5.6 GB |
| Updated | 2024-12-22 |
| Maintainer | zhoukz |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2 7B Instruct 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 7B Instruct Bnb 4bit | 32K / 5.5 GB | 166163 | 8 |
| Qwen2.5 Coder 7B Instruct 4bit | 32K / 4.3 GB | 89093 | 2 |
| Qwen2.5 7B Instruct 4bit | 32K / 4.3 GB | 12454 | 6 |
| Qwen UMLS 7B Instruct | 32K / 15.2 GB | 110 | 7 |
| Novaeus Promptist 7B Instruct | 32K / 15.2 GB | 149 | 8 |
| FinancialAdvice Qwen2.5 7B | 32K / 15.2 GB | 33 | 1 |
| ...2.5 Coder 7B Instruct Bnb 4bit | 32K / 5.5 GB | 8226 | 4 |
| Neumind Math 7B Instruct | 32K / 15.2 GB | 69 | 8 |
| Math IIO 7B Instruct | 32K / 15.2 GB | 85 | 7 |
| Qwen2.5 7B Instruct V1.2 | 32K / 15.2 GB | 403 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than zhoukz/qwen2-7b-instruct-4bit .
Rank the Qwen2 7B Instruct 4bit Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217